© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107152
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific principles and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nÄĽho
    -0.07
    rů
    -0.07
    baÅŁ
    -0.07
    stoff
    -0.07
     Ä°n
    -0.07
    istrovstvÃŃ
    -0.07
     köln
    -0.07
    _meas
    -0.07
     müc
    -0.07
     KiÅŁisel
    -0.07
    POSITIVE LOGITS
    orem
    0.08
    %C
    0.07
    ÑīинÑĭ
    0.07
    irit
    0.06
     entirety
    0.06
     aforementioned
    0.06
    :
    0.06
    ysi
    0.06
    ird
    0.06
    estone
    0.06
    Activations Density 0.001%

    No Known Activations